Tag
This study evaluates four proprietary LLMs (GPT-4o, GPT-5.2, Claude Sonnet 4.5, DeepSeek) for specialized terminology translation from English to French across two domains, comparing prompting strategies. Results show Claude Sonnet 4.5 performs best, but LLMs cannot yet replace specialized corpora.
A proposal to disambiguate the term 'graph engineering' into 'knowledge graph engineering' and 'agent graph engineering', referencing the 2026 surge in agent orchestration graphs and the confusion with traditional knowledge graphs.
A discussion on the varying definitions of 'AI agents' and whether everyone means the same thing when using the term.
This position paper argues that the term 'machine unlearning' is overused in LLM research, advocating for stricter terminology tied to dataset-defined deletion and retraining-equivalence guarantees.
Discusses two conflicting meanings of the term 'vibecoding'—one referring to careless code dumping on AI and another to significant AI assistance—and argues this ambiguity causes unnecessary friction in communication.
Linear design engineer Emil Kowalski compiled 90+ animation terms covering 12 categories. The author used Claude to create a bilingual preview site for understanding the effects.
Linear design engineer Emil Kowalski compiled over 90 animation terms across 12 categories to help users better describe animation effects to AI. Additionally, the author used Claude to build a bilingual preview site to facilitate understanding of each term's actual effect.
This paper proposes a method for curating a Cardiology Interface Terminology (CIT) to highlight details in electronic health record notes using a machine learning technique. The approach involves three phases, including deriving training data and training an ML model to identify candidate concepts, achieving high completeness and coverage on test data.
This is an open-source AI programming glossary that helps developers understand common concepts like context window, tool call, etc., organized by usage path and cross-linked.
Recommending a Huggingface article that explains common terms of AI Agent to help clarify concepts like Harness, Scaffold, Context Engineering, etc.
Armin Ronacher argues for replacing the term 'agent' with 'clanker' for LLM-based systems to emphasize they are tools, not responsible agents, and warns against anthropomorphizing AI.
A Hugging Face blog post that defines and clarifies key terms in the AI agent field, such as scaffolding, harness, context engineering, and tool use, aiming to standardize vocabulary amidst rapid evolution.
Compares DeepL, Gemini with basic prompt, and Gemini with glossary-augmented prompting for translating rock art Spanish-English terminology, finding that glossary-augmented prompting achieves the highest terminology accuracy (81.4%).
The author compiled a glossary of confusing LLM terms with production-oriented explanations, cleaned it up, and open-sourced it as a browsable UI on GitHub.
The article argues that most current 'Agentic AI' products are just basic automation loops with an LLM, not true autonomous agents, and criticizes the dilution of the term for marketing purposes.
The article discusses the controversy over the term 'distillation attacks,' arguing that labeling API abuse by some Chinese labs as 'distillation' risks stigmatizing a crucial and legitimate AI training technique. It calls for clearer terminology to distinguish between standard knowledge distillation and illicit API extraction methods like jailbreaking.